Using the same RDNA 2 microarchitecture as Microsoft's Xbox Series X and Sony's PlayStation 5 consoles, AMD is finally entering the high-end PC graphics card market with its Radeon RX 6000 series GPU. The 6000 family enables AMD to compete against the best graphics cards from rival Nvidia. It consists of the mainstream flagship Radeon RX 6800 XT, the high-end Radeon RX 6800 and the enthusiast-class Radeon RX 6900 XT. These GPUs support the Radeon family for the first time for ray tracing and support 4K games with 60 frames per second (fps).
The Radeon RX 6800 was developed as a competitor to last year's flagship Nvidia RTX 2080 Ti, while the Radeon RX 6800 XT will take over this year's RTX 3080 powerhouse. For avid gamers, data scientists and creatives who need even more power, the Radeon RX 6900 XT will compete against Nvidia's BFGPU, the GeForce RTX 3090.
The heart of the Radeon RX 6000 family is the RDNA 2 microarchitecture, also known as Navi 2x and colloquially known by gamers as "Big Navi". RDNA 2 is the second generation of the AMNA-RDNA architecture. Like moving from the older GCN architecture to RDNA, RDNA 2 offers significant performance gains. AMD claims that switching from GCN to RNDA resulted in a 50% improvement in performance per watt, and a similar boost is coming for players switching from RDNA to RDNA 2. For this generation, AMD is focused on gaining Nvidia's support for ray tracing, improving performance per watt, and better energy efficiency.
Price and availability: Radeon RX 6800 and 6800 XT
AMD announced during its October 28th event that its new PC graphics cards based on the RDNA 2 architecture will be available to gamers on November 18th. Prices for the Radeon RX 6800, a GPU designed to compete with the RTX 2080, start at just $ 579 Ti. For comparison, Nvidia launched the Founders Edition of its 2080 Ti card at $ 1,199. Dollar valued.
If you're looking for an AMD GPU to compete with Nvidia's current generation of GPUs, consider upgrading to the $ 649 Radeon RX 6800 XT. Because of its competitive performance, AMD is pricing this graphics card at the same price as Nvidia's flagship RTX 3080. In the past, AMD has been aggressively pricing, but it looks like this trend will end as the company can deliver better performance for its cards.
In press releases throughout the year, AMD CEO Lisa Su said that AMD has been slowly increasing the price of its GPUs over the past few years in an effort to achieve better margins as AMD recognizes that its investments in graphics add significant value to gamers. It looks like AMD is finally confident enough to raise the prices of its cards to match what its rival is doing in the space. So don't expect significant discounts across the board.
Hopefully, if these cards go up for sale, AMD will not suffer from the same supply shortages that have affected its rival. Before the Radeon launch event, AMD executives poked fun at Nvidia, stating that there will be enough inventory for its fans and gamers.
Price and availability: Radeon RX 6900 XT
The Radeon RX 6900 XT is the card for enthusiasts. In contrast to the other two cards in the RX 6000 family, the 6900 XT will be available a little later, on December 8th. The price for the card starts at $ 999.
For comparison: Nvidia's RTX 3090 costs $ 1,500. Choosing Team Red will save you $ 500. Depending on which AMD GPU you choose, it still makes sense to pick Team Red over its GeForce counterpart.
Radeon RX 6000 and the RDNA2 architecture
The Radeon 6000 brand was confirmed during the AMD event on October 28th where AMD unveiled its RDNA 2 architecture. "I'm very excited to show you the new RDNA 2 architecture and our full batch of Radeon RX 6000 series products," said Su in her keynote address, explaining that this is the most powerful line of graphics cards her company has ever built. “Many of you have asked us to do well on the top end of gaming GPUs. And today we're ready to show you exactly what we've been working on. "
With the Radeon RX 6000 family, AMD promises an aggressive improvement in performance per watt of at least 50% compared to the first generation RDNA family, higher energy efficiency compared to competing GPUs from Nvidia, and architecture changes that bring better bandwidth, Reduce bottlenecks and improve speeds. Overall, these changes will help AMD deliver on its promise of 4K gaming at 60 fps. On PCs, these GPUs start as the Radeon RX 6800, 6800 XT, and 6900 XT. AMD did not state whether further GPU variants will be added to the Radeon RX 6000 family in the future.
It's also unclear what strategy AMD will be pursuing for the Mac, as Apple recently announced it would begin the transition from Intel processors to its own Apple Silicon for the Mac. The RX 5000 series is available on the iMac as the Radeon Pro 5300, 5500XT, 5700, and 5700XT. When Apple's transition is complete, it will use its own integrated GPU solution on its custom ARM-based processors.
RX 6000 comes to APUs
In addition to premium GPUs and consoles, the Big Navi platform will be integrated into AMD's APUs as an integrated GPU solution, according to AMD CFO David Kumar. This is a move similar to what Intel is taking with its Intel Xe graphics architecture.
AMD's Ryzen 4000 APUs with integrated Radeon graphics offer enough power to play many 1080p titles with the game's lowest graphics settings. This would allow simple desktops – and mobile laptops – to play basic games without requiring an expensive or bulky setup with discrete GPUs. When AMD compared its Ryzen 7 4700G desktop APU to the Intel Core i7-9700, it showed that the GPU performance was up to 274% higher than the competition.
The RDNA 2-based APUs will likely give AMD an extra boost, but Intel's new integrated Xe architecture on its 11th generation processors also brings a significant performance leap with it. Intel's integrated Xe graphics, installed on Tiger Lake-based laptops this fall, promises to be 2.7 times faster than content creation, more than 20% better performance for office tasks, and twice as much Performance versus previous generation 11 integrated GPU. Intel's Xe platform has 96 execution cores for a total of 768 cores with 3.8MB L3 cache.
Intel's 11th generation Tiger Lake will likely compete against AMD's Renoir and Nvidia's discrete and lightweight GeForce MX in gaming. Intel's own numbers show that Xe outperforms the competition, including the Ryzen 7 4800U. Given that Intel is ramping up AMD on integrated GPU performance, it will be interesting to see how a future Ryzen APU with integrated RDNA 2 graphics will compete with the new Xe architecture.
AMD takes a different approach than Nvidia when it comes to memory. All of the company's latest 6000-series GPUs have a whopping 16 GB of memory, compared to just 10 GB on the flagship RTX 3080 and 8 GB on the RTX 3070.
However, AMD uses the slower GDDR6 memory format, while Nvidia has a slight advantage with GDDR6X memory on its high-end graphics card, at least on paper. AMD was unable to use the GDDR6X standard because it is available exclusively to Nvidia as part of a partnership with Micron. To address the memory speed bottleneck, AMD is using some hardware and software tricks to get more performance out of its 16GB of GDDR6 memory.
"We took a fresh approach to solving this technical gaming challenge by delivering a high-density, high-speed, graphics-optimized cache," said Laura Smith, Radeon chief engineer, during the AMD unveiling event. "We call this the Infinity Cache." AMD's Infinity Cache minimizes DRAM bottlenecks and latencies while reducing power consumption.
"Our specialized Infinity Cache, combined with a 256-bit G6 interface, offers more than twice the effective bandwidth of a traditional 384-bit G6 solution and uses less power," added Smith. Infinity Cache serves as a massive bandwidth amplifier, and AMD claimed that 256-bit GDDR6 16Gbps memory combined with 128MB Infinity Cache could result in 1664GB / s bandwidth.
This compares favorably to the GDDR6X performance on Nvidia's GPUs. For reference, the GDDR6X memory on Nvidia's RTX 3080 can run up to 760 GB per second. With the Infinity Cache enabled, AMD listed the memory bandwidth for all three graphics processors at 512 GB / s.
It used to be rumored that AMD's new cards might be available in HBM or high bandwidth memory, but recent leaks show these plans have been abandoned. HBM's high cost would likely have contributed to higher retail costs, which AMD may want to avoid as it competes against Nvidia in both price and performance. With Infinity Cache, it seems that AMD may not even have to resort to HBM to keep up, even if it has to do so with GDDR6 memory rather than GDDR6X.
Although RDNA 2 uses the same 7nm process node as the first generation RDNA platform, AMD says custom libraries and high-speed design flows help the new platform achieve 30% faster frequencies and up to 54% better performance per watt .
In contrast to Nvidia's controversial design with two axial fans, AMD is sticking to a more traditional GPU design with its graphics card. AMD announced that its 6000 family will be powered by three fans – all mounted on the same side. While Nvidia's latest GPUs have a subdued aesthetic as they chase data scientists, A.I. Engineers and non-gamers, AMD is sticking to a gaming-forward design with black accents, silver hardware, and red trim to highlight the Radeon badge. AMD previously confirmed that it will move away from a fan-style heat sink in favor of a higher quality design.
Another difference between AMD and Nvidia is that the new Radeon cards don't use a new power connector. Therefore, upgrades should be relatively easy. All three advertised cards use two 8-pin connectors.
While Nvidia uses a massive triple-slot format for its RTX 3090 GPU, AMD claims that its competing Radeon RX 6900 XT won't be much larger than the 6800 XT. "And you will see that for all the power it offers, it is actually relatively compact," said Su. "It's actually the same size as our 6800 XT card." Both the RX 6900 XT and RX 6800 XT use a 2.5-slot format, while the Radeon RX 6800 is smaller with a 2-slot format. All three cards are 267 mm long.
RDNA 2 is made using the same 7nm manufacturing process as the first generation product. AMD claims to have packed more than 26.8 billion transistors on its graphics chip in order to achieve 30% better energy efficiency than the cards of the previous generation. In terms of performance, AMD said that moving from older Vega GPUs based on the GCN platform to first generation RDNA brought a 50% increase in performance and a similar 50% improvement in performance per watt from RDNA to RDNA 2 is recorded.
The top-of-the-range Radeon RX 6900 XT comes with 80 processing units and 80 radiation accelerators with a boost clock rate of 2.25 GHz, 16 GB of memory with Infinity Cache and a TDP of 300 watts. The company claims this is the card for ultimate 4K gaming performance and has seen over 65% per watt performance increase over first generation RDNA GPUs. AMD claims this card could achieve 46.08 TFLOPS of the highest FP16 performance and 43.04 TFLOPS of the FP32 performance. It comes with 5,120 stream processors and 320 texture units.
"It's extremely competitive across the board, delivering consistently high frame rates and your favorite games," said Su. "Just look at the performance we're seeing against the competition in Battlefield 5, Call of Duty, and Gears of War 5. All of these have lower performance and a smaller card form factor."
The mainstream flagship of the Radeon RX 6800 XT has 72 processing units and 72 beam accelerators, a clock rate of over 2 GHz and a boost speed of 2.25 GHz, 16 GB of GDDR6 memory with 128 GB of Infinity Cache and a TDP of 300 watts . This card was developed for 4K games at 60 fps and is competitive with Nvidia's RTX 3080. Players who zoom out to 1440p games can see 100 fps in many games. The RX 6800 XT can achieve 41.47 TFLOPS of FP16 peak performance and 24.74 TFLOPS of FP32 peak performance. It has 4,608 stream processors and 288 texture units.
The last card in the Radeon RX 6000 family is the RX 6800. This card is clocked at 1.815 GHz and has a boost speed of 2.1 GHz. It has 60 processing units and comes with 16 GB of GDDR6 memory, using only 250 watts of electricity. AMD described this card as "a fantastic entry into 4K gaming" that offers 18% "more performance than the (Nvidia GeForce RTX) 2080 Ti". The RX 6800 has 3,840 stream processors, 60 beam accelerators and 240 texture units. This card can achieve 32.33 TFLOPS of FP16 performance and 16.17 TFLOPS of FP32 performance.
AMD also announced a one-click overclocking mode in Rage mode that can be activated through Radeon software, as well as AMD Smart Access Memory, which helps reduce game load times. This function is competitive with the functions of Nvidia with its ampere GPUs.
With both AMD features enabled, gamers can see up to a 13% increase in performance, according to the company. To reduce latency, AMD has also introduced its Radeon Anti-Lag and Radeon Boost technologies, which, together with FreeSync displays, enable latency reduction of up to 37% in competitive games such as Fortnite at 4K resolution. Radeon Boost is similar to Nvidia Reflex in that it analyzes your inputs – like mouse clicks – to improve on-screen latency and ensure you're ready to go. The tool is useful for action-packed games and esports.
AMD is working with partners like Microsoft to bring ray tracing to its GPUs for the first time.
"We worked closely with Microsoft on the ultimate features of Direct X 12, including Direct X ray tracing, variable rate shading, mesh shaders and support for Microsoft Direct Storage APIs," said Smith, chief engineer at Radeon.
The company also expanded its library of Fidelity FX features to work hand-in-hand with ray-traced compute and shader effects for better visual fidelity for games. According to AMD, variable rate denoiser and shading algorithms help adjust image quality based on luminance and motion, and a number of computational effects are also available to developers.
And like rival Nvidia, AMD will also use Microsoft's Direct Storage API to reduce game load times.
AMD did not disclose details of the implementation of ray tracing during the Radeon RX 6000 product launch.
With RDNA 2, AMD has the chance to take over Nvidia in the premium segment. While AMD has an excellent track record in the midrange market, the RDNA 2 architecture allows AMD to compete at any cost. While AMD's current offering for gamers is strong in the 1080p and 2K 1440p segments, Big Navi will bring "uncompromising 4K gaming" according to a slide the company has shown investors.
When AMD unveiled its RX 6000 family, Su announced that AMD’s latest Radeon graphics card offers a 50% increase in performance for generations. The first-class Radeon RX 6900 XT offers a performance increase of 64% per watt compared to the first generation of RDNA. With AMD's focus on energy efficiency, the Radeon cards can also reduce power consumption by 30% while maintaining performance that is competitive with Nvidia's cards.
During the company's presentation, AMD revealed that the 4K and 1440p performance of the Radeon RX 6800 XT was very competitive against Nvidia's RTX 3080. Both cards achieved similar frame rates across a range of different game titles.
The AMD metrics were in line with rumors reported by Igor & # 39; s Lab and Hardware Times that the latest Radeon can compete with the RTX 3080 in terms of performance. Above all, AMD is able to match the performance of the 320-watt RTX flagship with just 300 watts, which corresponds to the same power consumption as the Radeon VII.
Although AMD positions its RX 6900 XT against Nvidia's RTX 3090, it is unclear how the Radeon card will perform. AMD showed that both cards performed similarly in gameplay at 4K at the highest game settings, with the 6900 XT ahead of its rival. However, Nvidia positions its RTX 3090 as an 8K card with 60 fps. AMD didn't go up to 8K in its published benchmarks.